Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/destructiveHint=false, and 'Lecture seule' simply echoes that. The real added value is 'Indicatif — reglement ERP et CCTP signes priment', which tells the agent the returned verdicts are advisory and may be overridden by ERP regulation or signed CCTP documents — a material behavioral caveat an agent must know before acting on results. Return format is not described, but no output schema exists and this is a read-only check.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Telegraphic and front-loaded: the activation condition comes first, then the domain list, then the object shape, then the disclaimer. No filler sentences. The object shape is stated twice (once via AD-* codes, once via sub-keys), a minor redundancy that does serve to map regulation articles to keys.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only check with annotations covering the safety profile, the description supplies what matters: what is checked, that results are indicative versus ERP/CCTP. Remaining gaps are the behavior with an empty/absent 'scene' argument and what the response contains, but neither is critical for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'scene' parameter is already described as the auditorium object with its four sub-keys; the description restates that structure without adding syntax, expected value types, or a convention for the AD-* codes. Baseline 3 applies since the schema does the documentation work. It also never says what happens if 'scene' is omitted (0 required parameters).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ('VERIFIER') plus resource ('AUDITORIUM / salle de spectacle') and an explicit enumeration of the four domains covered (acoustique, eclairage, ventilation, securite) with their regulation codes. It clearly reads as an aggregate multi-domain check rather than a single-topic one. It stops short of naming which sibling does single-topic checks (e.g. cao_bim_acoustique, cao_bim_eclairage), leaving the boundary implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Appelez quand vous devez VERIFIER L'AUDITORIUM' gives a positive call condition, which is better than nothing. However, there is no when-not guidance and no reference to the many narrower siblings (cao_bim_acoustique, cao_bim_ventilation_*, cao_bim_incendie) that an agent should prefer for a single aspect, so the choice among them is left to inference. The 'Indicatif' caveat hints that authoritative checks happen elsewhere, but doesn't say where.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.